# opendilab/PPOxFamily

PPO x Family DRL Tutorial Course（决策智能入门级公开课：8节课帮你盘清算法理论，理顺代码逻辑，玩转决策AI应用实践 ）

Repository: https://github.com/opendilab/PPOxFamily
Canonical: https://ross.abutalabs.com/products/ppoxfamily
Homepage: https://opendilab.github.io/PPOxFamily/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: course, decision-intelligence, python, reinforcement-learning, deep-reinforcement-learning
Last push: 2025-03-13T10:38:57+00:00

## Health v2 (maintenance only)
Score: 37/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 11, release rhythm 35, longevity 99
- inputs: {"age_days": 1388, "days_push": 538, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2614, forks 217 (observed 2026-08-28T04:07:04.523835+00:00)

## What it is
PPO x Family is an open-source introductory course on decision intelligence and deep reinforcement learning, centered on the PPO algorithm family. It combines video lectures, annotated PyTorch code documentation, exercises, and datasets to teach how one PPO algorithm can solve a wide range of decision-making applications.

## Use cases
- learn deep reinforcement learning from scratch
- understand the PPO algorithm in depth
- study annotated PyTorch implementations of policy gradient methods
- apply PPO to discrete, continuous, and hybrid action spaces
- learn multi-agent reinforcement learning
- find course exercises and datasets for DRL practice

## When to choose
- you want a structured, beginner-friendly DRL course focused on PPO
- you prefer learning through annotated code alongside theory
- you want free video lectures with exercises and datasets

## When to avoid
- you need a production-ready RL training library rather than course material
- you want broad coverage of RL algorithms beyond the PPO family
- you need non-Python or non-PyTorch examples

## Facets
- artifact type: learning-resource
- maturity: active
- function: reinforcement-learning, machine-learning
- domain: reinforcement-learning, tutorials, artificial-intelligence, education
- platform: python, cross-platform
- tags: ppo, deep-reinforcement-learning, tutorial-course, pytorch, decision-intelligence, annotated-code, video-course, education

## Member repositories
- opendilab/PPOxFamily (main) score 37

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:04.523835+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:20:34.573909+00:00, confidence not recorded.
  - readme: https://github.com/opendilab/PPOxFamily (fetched 2026-08-28T04:07:04.523835+00:00, sha 47b0d247f53c)
  - homepage: https://opendilab.github.io/PPOxFamily/ (fetched 2026-08-29T10:03:27.115909+00:00, sha bcffdc739793)
- Data as of 2026-08-30T08:39:29.467469+00:00.